PyMuPDF4LLMLoader 集成

使用 LangChain Python 集成 PyMuPDF4LLMLoader 文档加载器。

This guide provides a quick overview for getting started with the PyMuPDF4LLMLoader document loader. For detailed documentation of all PyMuPDF4LLMLoader features and configurations head to the GitHub repository.

概述

集成详情

Class	Package	Local	Serializable	JS support
PyMuPDF4LLMLoader	langchain-pymupdf4llm	✅	❌	❌

加载器特性

Source	Document Lazy Loading	Native Async Support	Extract Images	Extract Tables
PyMuPDF4LLMLoader	✅	❌	✅	✅

设置

To access PyMuPDF4LLM document loader you’ll need to install the langchain-pymupdf4llm integration package.

凭证

No credentials are required to use PyMuPDF4LLMLoader.

要启用模型调用的自动追踪，请设置你的 LangSmith API 密钥：

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

安装

安装 langchain-community and langchain-pymupdf4llm。

pip install -qU langchain-community langchain-pymupdf4llm

初始化

现在我们可以实例化模型对象并加载文档：

from langchain_pymupdf4llm import PyMuPDF4LLMLoader

file_path = "./example_data/layout-parser-paper.pdf"
loader = PyMuPDF4LLMLoader(file_path)

加载

docs = loader.load()
docs[0]

Document(metadata={'producer': 'pdfTeX-1.40.21', 'creator': 'LaTeX with hyperref', 'creationdate': '2021-06-22T01:27:10+00:00', 'source': './example_data/layout-parser-paper.pdf', 'file_path': './example_data/layout-parser-paper.pdf', 'total_pages': 16, 'format': 'PDF 1.5', 'title': '', 'author': '', 'subject': '', 'keywords': '', 'moddate': '2021-06-22T01:27:10+00:00', 'trapped': '', 'modDate': 'D:20210622012710Z', 'creationDate': 'D:20210622012710Z', 'page': 0}, page_content='\`\`\`\nLayoutParser: A Unified Toolkit for Deep\n\n## Learning Based Document Image Analysis\n\n\`\`\`\n\nZejiang Shen[1] (�), Ruochen Zhang[2], Melissa Dell[3], Benjamin Charles Germain\nLee[4], Jacob Carlson[3], and Weining Li[5]\n\n1 Allen Institute for AI\n\`\`\`\n              [e-mail]\n\n\`\`\`\n2 Brown University\n\`\`\`\n             ruochen [e-mail]\n\n\`\`\`\n3 Harvard University\n_{melissadell,jacob carlson}@fas.harvard.edu_\n4 University of Washington\n\`\`\`\n              [e-mail]\n\n\`\`\`\n5 University of Waterloo\n\`\`\`\n              [e-mail]\n\n\`\`\`\n\n**Abstract. Recent advances in document image analysis (DIA) have been**\nprimarily driven by the application of neural networks. Ideally, research\noutcomes could be easily deployed in production and extended for further\ninvestigation. However, various factors like loosely organized codebases\nand sophisticated model configurations complicate the easy reuse of important innovations by a wide audience. Though there have been on-going\nefforts to improve reusability and simplify deep learning (DL) model\ndevelopment in disciplines like natural language processing and computer\nvision, none of them are optimized for challenges in the domain of DIA.\nThis represents a major gap in the existing toolkit, as DIA is central to\nacademic research across a wide range of disciplines in the social sciences\nand humanities. This paper introduces LayoutParser, an open-source\nlibrary for streamlining the usage of DL in DIA research and applications. The core LayoutParser library comes with a set of simple and\nintuitive interfaces for applying and customizing DL models for layout detection, character recognition, and many other document processing tasks.\nTo promote extensibility, LayoutParser also incorporates a community\nplatform for sharing both pre-trained models and full document digitization pipelines. We demonstrate that LayoutParser is helpful for both\nlightweight and large-scale digitization pipelines in real-word use cases.\n[The library is publicly available at https://layout-parser.github.io.](https://layout-parser.github.io)\n\n**Keywords: Document Image Analysis · Deep Learning · Layout Analysis**\n\n    - Character Recognition · Open Source library · Toolkit.\n\n### 1 Introduction\n\n\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\ndocument image analysis (DIA) tasks including document image classification [11,\n\n')

import pprint

pprint.pp(docs[0].metadata)

{'producer': 'pdfTeX-1.40.21',
 'creator': 'LaTeX with hyperref',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'file_path': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'format': 'PDF 1.5',
 'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'moddate': '2021-06-22T01:27:10+00:00',
 'trapped': '',
 'modDate': 'D:20210622012710Z',
 'creationDate': 'D:20210622012710Z',
 'page': 0}

惰性加载

pages = []
for doc in loader.lazy_load():
    pages.append(doc)
    if len(pages) >= 10:
        # do some paged operation, e.g.
        # index.upsert(page)

        pages = []
len(pages)

6

from IPython.display import Markdown, display

part = pages[0].page_content[778:1189]
print(part)
# Markdown rendering
display(Markdown(part))

pprint.pp(pages[0].metadata)

{'producer': 'pdfTeX-1.40.21',
 'creator': 'LaTeX with hyperref',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'file_path': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'format': 'PDF 1.5',
 'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'moddate': '2021-06-22T01:27:10+00:00',
 'trapped': '',
 'modDate': 'D:20210622012710Z',
 'creationDate': 'D:20210622012710Z',
 'page': 10}

metadata 属性至少包含以下键：

• source
• page (if in mode page)
• total_page
• creationdate
• creator
• producer

额外的元数据因解析器而异。 这些信息可能很有用（例如用于分类你的 PDF）。

Splitting mode & custom pages delimiter

加载 PDF 文件时，你可以用两种不同的方式分割它：

• By page
• As a single text flow

默认情况下，PyMuPDF4LLMLoader will split the PDF by page.

Extract the PDF by page. each page is extracted as a langchain document object

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
)
docs = loader.load()

print(len(docs))
pprint.pp(docs[0].metadata)

16
{'producer': 'pdfTeX-1.40.21',
 'creator': 'LaTeX with hyperref',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'file_path': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'format': 'PDF 1.5',
 'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'moddate': '2021-06-22T01:27:10+00:00',
 'trapped': '',
 'modDate': 'D:20210622012710Z',
 'creationDate': 'D:20210622012710Z',
 'page': 0}

In this mode the pdf is split by pages and the resulting Documents metadata contains the page (page number). But in some cases we could want to process the pdf as a single text flow (so we don’t cut some paragraphs in half). In this case you can use the single mode :

Extract the whole PDF as a single langchain document object

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="single",
)
docs = loader.load()

print(len(docs))
pprint.pp(docs[0].metadata)

1
{'producer': 'pdfTeX-1.40.21',
 'creator': 'LaTeX with hyperref',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'file_path': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'format': 'PDF 1.5',
 'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'moddate': '2021-06-22T01:27:10+00:00',
 'trapped': '',
 'modDate': 'D:20210622012710Z',
 'creationDate': 'D:20210622012710Z'}

Logically, in this mode, the page (page_number) metadata disappears. Here’s how to clearly identify where pages end in the text flow :

Add a custom pages_delimiter to identify where are ends of pages in single mode

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="single",
    pages_delimiter="\n-------THIS IS A CUSTOM END OF PAGE-------\n\n",
)
docs = loader.load()

part = docs[0].page_content[10663:11317]
print(part)
display(Markdown(part))

默认pages_delimiter is \n-----\n\n. This could simply be \n, or \f to clearly indicate a page change, or <!— PAGE BREAK —> for seamless injection in a Markdown viewer without a visual effect.

Extract images from the PDF

You can extract images from your PDFs (in text form) with a choice of three different solutions:

• rapidOCR (lightweight Optical Character Recognition tool)
• Tesseract (OCR tool with high precision)
• Multimodal language model

The result is inserted at the end of text of the page.

Extract images from the PDF with rapidOCR

pip install -qU rapidocr-onnxruntime pillow

from langchain_community.document_loaders.parsers import RapidOCRBlobParser

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
    extract_images=True,
    images_parser=RapidOCRBlobParser(),
)
docs = loader.load()

part = docs[5].page_content[1863:]
print(part)
display(Markdown(part))

请注意，RapidOCR 设计用于处理中文和英文，不支持其他语言。

Extract images from the PDF with tesseract

pip install -qU pytesseract

from langchain_community.document_loaders.parsers import TesseractBlobParser

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
    extract_images=True,
    images_parser=TesseractBlobParser(),
)
docs = loader.load()

print(docs[5].page_content[1863:])

Extract images from the PDF with multimodal model

pip install -qU langchain-openai

import os

from dotenv import load_dotenv

load_dotenv()

True

from getpass import getpass

if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass("OpenAI API key =")

from langchain_community.document_loaders.parsers import LLMImageBlobParser
from langchain_openai import ChatOpenAI

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
    extract_images=True,
    images_parser=LLMImageBlobParser(
        model=ChatOpenAI(model="gpt-5.4-mini", max_tokens=1024)
    ),
)
docs = loader.load()

print(docs[5].page_content[1863:])

Extract tables from the PDF

With PyMUPDF4LLM you can extract tables from your PDFs in markdown format :

loader = PyMuPDF4LLMLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
    # "lines_strict" is the default strategy and
    # is the most accurate for tables with column and row lines,
    # but may not work well with all documents.
    # "lines" is a less strict strategy that may work better with
    # some documents.
    # "text" is the least strict strategy and may work better
    # with documents that do not have tables with lines.
    table_strategy="lines",
)
docs = loader.load()

part = docs[4].page_content[3210:]
print(part)
display(Markdown(part))

Working with files

许多文档加载器涉及文件解析。这类加载器之间的差异通常在于文件的解析方式，而不是文件的加载方式。 For example, you can use open to read the binary content of either a PDF or a markdown file, but you need different parsing logic to convert that binary data into text.

As a result, it can be helpful to decouple the parsing logic from the loading logic, which makes it easier to reuse a given parser regardless of how the data was loaded. 你可以使用此策略用相同的解析参数分析不同的文件。

from langchain_community.document_loaders import FileSystemBlobLoader
from langchain_community.document_loaders.generic import GenericLoader
from langchain_pymupdf4llm import PyMuPDF4LLMParser

loader = GenericLoader(
    blob_loader=FileSystemBlobLoader(
        path="./example_data/",
        glob="*.pdf",
    ),
    blob_parser=PyMuPDF4LLMParser(),
)
docs = loader.load()

part = docs[0].page_content[:562]
print(part)
display(Markdown(part))

---

API 参考

For detailed documentation of all PyMuPDF4LLMLoader features and configurations head to the GitHub repository: github.com/lakinduboteju/langchain-pymupdf4llm

---

通过 MCP 将这些文档连接到 Claude、VSCode 等工具以获取实时答案。

在 GitHub 上编辑此页面 或 提交 issue。